Scholarlink

In this research work, it aims to address and bridge the gap in the medical market by proposing a new framework for Ensemble Deep Autoencoder that is capable of accurately identifying prostate cancer in magnetic resonance imaging (MRI) data. The proposed autoencoders methodology plays a crucial and major role in detecting prostate cancer which are observed in MRI scans. This technique not only improves the extraction of features, but it also lessens the impact of variability in magnetic resonance imaging (MRI) images of the prostate cancer. A novel approach on Ensemble Deep Autoencoders (EDA) and techniques has been proposed. The proposed EDAE method is compared other existing techniques like SVM and CNN. The proposed EDA method achieves 5 to 15% of high values than other CNN and SVM across all tested datasets.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Ensemble Deep Learning Approach for Prostate Cancer Detection in MRI Images

  • 章节

  • 发表日期：

    2025年

查看全文
  • N. R. Wilfred Blessing,
  • K. P. Arjun,
  • N. M. Sreenarayanan,
  • G. Sutherlin Subitha,
  • Neethu Narayanan,
  • Manu Mundappat Ramachandran

摘要

In this research work, it aims to address and bridge the gap in the medical market by proposing a new framework for Ensemble Deep Autoencoder that is capable of accurately identifying prostate cancer in magnetic resonance imaging (MRI) data. The proposed autoencoders methodology plays a crucial and major role in detecting prostate cancer which are observed in MRI scans. This technique not only improves the extraction of features, but it also lessens the impact of variability in magnetic resonance imaging (MRI) images of the prostate cancer. A novel approach on Ensemble Deep Autoencoders (EDA) and techniques has been proposed. The proposed EDAE method is compared other existing techniques like SVM and CNN. The proposed EDA method achieves 5 to 15% of high values than other CNN and SVM across all tested datasets.